1 code implementation • NLPerspectives (LREC) 2022 • Kamil Kanclerz, Marcin Gruza, Konrad Karanowski, Julita Bielaniewicz, Piotr Milkowski, Jan Kocon, Przemyslaw Kazienko
This supports our overall observation that personalized models should always be considered in all subjective NLP tasks, including hate speech detection.
no code implementations • 18 Dec 2023 • Julita Bielaniewicz, Przemysław Kazienko
It seems that concatenating personalized datasets, even with the cost of normalizing the range of annotations across all datasets, if combined with the personalized models, results in an enormous increase in the performance of humor detection.
1 code implementation • 13 Dec 2023 • Kamil Kanclerz, Julita Bielaniewicz, Marcin Gruza, Jan Kocon, Stanisław Woźniak, Przemysław Kazienko
Data annotated by humans is a source of knowledge by describing the peculiarities of the problem and therefore fueling the decision process of the trained model.
1 code implementation • Conference on Empirical Methods in Natural Language Processing (EMNLP) 2023 • Kamil Kanclerz, Konrad Karanowski, Julita Bielaniewicz, Marcin Gruza, Piotr Miłkowski, Jan Kocon, Przemyslaw Kazienko
In this paper, we present novel Personalized Active Learning techniques for Subjective NLP tasks (PALS) to either reduce the cost of the annotation process or to boost the learning effect.
1 code implementation • 21 Feb 2023 • Jan Kocoń, Igor Cichecki, Oliwier Kaszyca, Mateusz Kochanek, Dominika Szydło, Joanna Baran, Julita Bielaniewicz, Marcin Gruza, Arkadiusz Janz, Kamil Kanclerz, Anna Kocoń, Bartłomiej Koptyra, Wiktoria Mieleszczenko-Kowszewicz, Piotr Miłkowski, Marcin Oleksy, Maciej Piasecki, Łukasz Radliński, Konrad Wojtasik, Stanisław Woźniak, Przemysław Kazienko
Our comparison of its results with available State-of-the-Art (SOTA) solutions showed that the average loss in quality of the ChatGPT model was about 25% for zero-shot and few-shot evaluation.